SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Honeycomb is building the next generation of observability tools, and the Agentic Intelligence team is at the forefront of that effort. This role focuses on designing and delivering production-grade AI agents that investigate, reason, and act on real observability data within Canvas, Honeycomb's agentic workspace.
You'll own the full lifecycle of agent development—from prototyping through production deployment. This includes designing agents that leverage Honeycomb's high-cardinality data store to enable capabilities no other observability product can match. You'll build agents that correlate signals across services, drill into individual traces, and compare before/after deployment states with speed and precision.
Key responsibilities include:
- Designing and shipping production-grade agents that engineers can trust in high-pressure, mid-incident situations
- Owning agent scope, implementation, shipping, and maintenance, including evaluation frameworks that measure real improvement
- Extending Canvas surface area, the MCP server, and Canvas Skills with new capabilities like memory and spatial awareness
- Establishing quality standards for agents: measurable evals, maintainability, and honest limitation documentation
- Distinguishing genuine signal from hype in a rapidly evolving AI/agent landscape
The work spans from rough prototypes to production systems, with some fullstack development alongside agent-focused work. You'll have the autonomy to propose and validate what comes next using working code. Honeycomb is a 200+ person, Series D-funded company serving customers like Slack, HelloFresh, LaunchDarkly, and Vanguard. The company is fully distributed and values delivery, culture fit, and trust from day one.
